Downloads · 30 days
83
4% of all-time downloads
DeepSeek-V4-Flash-DSpark-FP8-dspark_only
AtlasCloud/DeepSeek-V4-Flash-DSpark-FP8-dspark_only
DeepSeek-V4-Flash-DSpark-FP8-dspark_only is a machine learning model from AtlasCloud. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for sglang.
This repository contains only the mtp. DSpark draft tensors from deepseek-ai/DeepSeek-V4-Flash-DSpark. Its routed-expert E2M1 FP4 tensors were losslessly represented as block-scaled E4M3 FP8 tensors using SGLang's cas…
All-time downloads
1.9K
Public
Parameters
19.8B
19.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors19.9 GB · 100%
Parameter types
How the weights are stored.
F8_E4M319.8B · 100%
Base models
Model card
From the Hugging Face model README
DeepSeek-V4-Flash DSpark draft-only FP8
This repository contains only the mtp.* DSpark draft tensors from
deepseek-ai/DeepSeek-V4-Flash-DSpark. Its routed-expert E2M1 FP4 tensors
were losslessly represented as block-scaled E4M3 FP8 tensors using SGLang's
cast_e2m1fn_to_e4m3fn conversion.
Use it with an FP8 target checkpoint:
python3 -m sglang.launch_server \
--model-path sgl-project/DeepSeek-V4-Flash-FP8 \
--speculative-algorithm DSPARK \
--speculative-draft-model-path AtlasCloud/DeepSeek-V4-Flash-DSpark-FP8-dspark_only
The target checkpoint must provide the compatible tokenizer, embedding, and LM head; this draft-only checkpoint intentionally excludes them.
- Library
- sglang
- Type
- deepseek_v4
- Created
- Jul 27, 2026
- Updated
- Jul 27, 2026